AIBullisharXiv – CS AI · 8h ago6/10
🧠
Scaling Novel Graph Generation via Lightweight Structure-Guided Autoregressive Models
Researchers propose a lightweight autoregressive framework for graph generation that achieves near log-linear complexity by using structure-guided topological ordering, addressing scalability limitations in current diffusion and autoregressive models. The two-phase training strategy reduces overfitting and promotes novel graph generation while maintaining validity, with applications spanning molecular discovery, circuit design, and cybersecurity.